Skip to content

Add gpt-oss to vLLM dashboard #74

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Sep 3, 2025
Merged

Add gpt-oss to vLLM dashboard #74

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
622bd7e
Add gpt-oss to vLLM dashboard
huydhn Sep 3, 2025
756ea00
Typo
huydhn Sep 3, 2025
2b84343
Default to h100
huydhn Sep 3, 2025
e4ee3d8
Typo
huydhn Sep 3, 2025
8c6758f
Set input and output lengths
huydhn Sep 3, 2025
0254991
Another tweak
huydhn Sep 3, 2025
c3bee8f
Another tweak
huydhn Sep 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/vllm-benchmark.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ jobs:
shell: bash
env:
MODELS: ${{ inputs.models || '' }}
RUNNERS: ${{ inputs.runners || '' }}
RUNNERS: ${{ inputs.runners || 'h100' }}
run: |
set -eux

Expand Down
22 changes: 22 additions & 0 deletions vllm-benchmarks/benchmarks/cuda/latency-tests.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,5 +50,27 @@
"num_iters": 15,
"max_model_len": 8192
}
},
{
"test_name": "latency_gpt_oss_20b_tp1",
"parameters": {
"model": "openai/gpt-oss-20b",
"tensor_parallel_size": 1,
"load_format": "dummy",
"num_iters_warmup": 5,
"num_iters": 15,
"max_model_len": 8192
}
},
{
"test_name": "latency_gpt_oss_120b_tp4",
"parameters": {
"model": "openai/gpt-oss-120b",
"tensor_parallel_size": 4,
"load_format": "dummy",
"num_iters_warmup": 5,
"num_iters": 15,
"max_model_len": 8192
}
}
]
40 changes: 40 additions & 0 deletions vllm-benchmarks/benchmarks/cuda/serving-tests.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -411,5 +411,45 @@
"random_input_len": 30720,
"random_output_len": 100
}
},
{
"test_name": "serving_gpt_oss_20b_tp1_random_in5k_out8k",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "openai/gpt-oss-20b",
"tensor_parallel_size": 1,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy"
},
"client_parameters": {
"model": "openai/gpt-oss-20b",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 5250,
"random_output_len": 8250
}
},
{
"test_name": "serving_gpt_oss_120b_tp4_random_in5k_out8k",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "openai/gpt-oss-120b",
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy"
},
"client_parameters": {
"model": "openai/gpt-oss-120b",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 5250,
"random_output_len": 8250
}
}
]
24 changes: 24 additions & 0 deletions vllm-benchmarks/benchmarks/cuda/throughput-tests.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,5 +55,29 @@
"backend": "vllm",
"max_model_len": 8192
}
},
{
"test_name": "throughput_gpt_oss_20b_tp1",
"parameters": {
"model": "openai/gpt-oss-20b",
"tensor_parallel_size": 1,
"load_format": "dummy",
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm",
"max_model_len": 8192
}
},
{
"test_name": "throughput_gpt_oss_120b_tp4",
"parameters": {
"model": "openai/gpt-oss-120b",
"tensor_parallel_size": 4,
"load_format": "dummy",
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm",
"max_model_len": 8192
}
}
]